Provider guide
Where to run GPT-5.6 Terra
7 live offers tracked — output prices vary 2.2× between the cheapest and most expensive host, so the provider choice matters as much as the model choice.
FASTEST MEASURED
99 tok/s
measured throughput · $2.20 input / $13.20 output per million tokens
OpenRouterCHEAPEST$1.00 in/1M$6.00 out/1M—1.1M—59m agoOpenAI$2.00 in/1M$12.00 out/1M—1.1M—7h agoAmazon Bedrock$2.20 in/1M$13.20 out/1M99 tok/s1.1M—57m agoOpenAIflex tier$0.50 in/1M$3.00 out/1M71 tok/s1.1M—7h agoMicrosoft Azure AIzero-retention$2.50 in/1M$15.00 out/1M58 tok/s1.1M—57m agoMicrosoft Azure AIzero-retention$2.75 in/1M$16.50 out/1M7 tok/s1.1M—57m agoOpenAIpriority tier$5.00 in/1M$30.00 out/1M—1.1M—8d ago
Microsoft Azure AIFull specs, hardware verdicts and benchmarks on theGPT-5.6 Terra model page →